def crawl():
#Use logger to debug the code
Logger.debug('Hello google')
#Get the html knowledge by parsing url
soup = get_b_soup('http://www.google.com')
#Send the data to output pipe line
Queues.send_to_output(soup.head.title.text)
Queues.send_to_output('http://www.google.com' + soup.head.meta['content'])
def crawl():
#Use logger to debug the code
Logger.debug('Hello google')
#Get the html knowledge by parsing url
soup = get_b_soup('http://www.google.com')
#Send the data to output pipe line
Queues.send_to_output(soup.head.title.text)
Queues.send_to_output('http://www.google.com' + soup.head.meta['content'])
def execute_output():
Logger()
Logger.debug('Start Output Process')
while True:
try:
result = Queues.get_output()
Logger.info(result)
#Your output logic go there
except:
break
Logger.debug('End Output Process')
def main():
#Create Logger file and output queue
Logger(parent=True)
Queues()
#target is in the output.py file
output_process = Process(target=output.execute_output, name='OutputProcess')
output_process.start()
pool = MyPool(processes=config.NUMBER_OF_WORKERS)
pool.map(worker, get_bot_list())
output_process.join()
def execute_output():
Logger()
Logger.debug('Start Output Process')
while True:
try:
result = Queues.get_output()
Logger.info(result)
#Your output logic go there
except:
break
Logger.debug('End Output Process')
def crawl(soup):
#Get the beautiful soup
title = soup.find('meta', {'name': 'title'})['content']
#And send it via the output pipe
Queues.send_to_output(title)